1 files changed, 20 insertions, 18 deletions

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index a3046142cb8e..35dd89aff4a9 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -392,14 +392,12 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
 		}
 		/* Restore Eth hdr pulled by dev_forward_skb/eth_type_trans */
 		__skb_push(skb, ETH_HLEN);
-		/* Depend on prior success packets started NAPI consumer via
-		 * __veth_xdp_flush(). Cancel TXQ stop if consumer stopped,
-		 * paired with empty check in veth_poll().
-		 */
 		netif_tx_stop_queue(txq);
-		smp_mb__after_atomic();
-		if (unlikely(__ptr_ring_empty(&rq->xdp_ring)))
-			netif_tx_wake_queue(txq);
+		/* Makes sure NAPI peer consumer runs. Consumer is responsible
+		 * for starting txq again, until then ndo_start_xmit (this
+		 * function) will not be invoked by the netstack again.
+		 */
+		__veth_xdp_flush(rq);
 		break;
 	case NET_RX_DROP: /* same as NET_XMIT_DROP */
 drop:
@@ -900,17 +898,9 @@ static int veth_xdp_rcv(struct veth_rq *rq, int budget,
 			struct veth_xdp_tx_bq *bq,
 			struct veth_stats *stats)
 {
-	struct veth_priv *priv = netdev_priv(rq->dev);
-	int queue_idx = rq->xdp_rxq.queue_index;
-	struct netdev_queue *peer_txq;
-	struct net_device *peer_dev;
 	int i, done = 0, n_xdpf = 0;
 	void *xdpf[VETH_XDP_BATCH];
 
-	/* NAPI functions as RCU section */
-	peer_dev = rcu_dereference_check(priv->peer, rcu_read_lock_bh_held());
-	peer_txq = peer_dev ? netdev_get_tx_queue(peer_dev, queue_idx) : NULL;
-
 	for (i = 0; i < budget; i++) {
 		void *ptr = __ptr_ring_consume(&rq->xdp_ring);
 
@@ -959,9 +949,6 @@ static int veth_xdp_rcv(struct veth_rq *rq, int budget,
 	rq->stats.vs.xdp_packets += done;
 	u64_stats_update_end(&rq->stats.syncp);
 
-	if (peer_txq && unlikely(netif_tx_queue_stopped(peer_txq)))
-		netif_tx_wake_queue(peer_txq);
-
 	return done;
 }
 
@@ -969,12 +956,20 @@ static int veth_poll(struct napi_struct *napi, int budget)
 {
 	struct veth_rq *rq =
 		container_of(napi, struct veth_rq, xdp_napi);
+	struct veth_priv *priv = netdev_priv(rq->dev);
+	int queue_idx = rq->xdp_rxq.queue_index;
+	struct netdev_queue *peer_txq;
 	struct veth_stats stats = {};
+	struct net_device *peer_dev;
 	struct veth_xdp_tx_bq bq;
 	int done;
 
 	bq.count = 0;
 
+	/* NAPI functions as RCU section */
+	peer_dev = rcu_dereference_check(priv->peer, rcu_read_lock_bh_held());
+	peer_txq = peer_dev ? netdev_get_tx_queue(peer_dev, queue_idx) : NULL;
+
 	xdp_set_return_frame_no_direct();
 	done = veth_xdp_rcv(rq, budget, &bq, &stats);
 
@@ -996,6 +991,13 @@ static int veth_poll(struct napi_struct *napi, int budget)
 		veth_xdp_flush(rq, &bq);
 	xdp_clear_return_frame_no_direct();
 
+	/* Release backpressure per NAPI poll */
+	smp_rmb(); /* Paired with netif_tx_stop_queue set_bit */
+	if (peer_txq && netif_tx_queue_stopped(peer_txq)) {
+		txq_trans_cond_update(peer_txq);
+		netif_tx_wake_queue(peer_txq);
+	}
+
 	return done;
 }